1 /* Line breaking of UTF-8 strings.
2 Copyright (C) 2001-2003, 2006-2011 Free Software Foundation, Inc.
3 Written by Bruno Haible <bruno@clisp.org>, 2001.
5 This program is free software: you can redistribute it and/or modify it
6 under the terms of the GNU Lesser General Public License as published
7 by the Free Software Foundation; either version 3 of the License, or
8 (at your option) any later version.
10 This program is distributed in the hope that it will be useful,
11 but WITHOUT ANY WARRANTY; without even the implied warranty of
12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 Lesser General Public License for more details.
15 You should have received a copy of the GNU Lesser General Public License
16 along with this program. If not, see <http://www.gnu.org/licenses/>. */
27 u8_width_linebreaks (const uint8_t *s, size_t n,
28 int width, int start_column, int at_end_columns,
29 const char *o, const char *encoding,
37 u8_possible_linebreaks (s, n, encoding, p);
41 last_column = start_column;
46 int count = u8_mbtouc_unsafe (&uc, s, s_end - s);
48 /* Respect the override. */
49 if (o != NULL && *o != UC_BREAK_UNDEFINED)
52 if (*p == UC_BREAK_POSSIBLE || *p == UC_BREAK_MANDATORY)
54 /* An atomic piece of text ends here. */
55 if (last_p != NULL && last_column + piece_width > width)
57 /* Insert a line break. */
58 *last_p = UC_BREAK_POSSIBLE;
63 if (*p == UC_BREAK_MANDATORY)
65 /* uc is a line break character. */
66 /* Start a new piece at column 0. */
73 /* uc is not a line break character. */
76 if (*p == UC_BREAK_POSSIBLE)
78 /* Start a new piece. */
80 last_column += piece_width;
82 /* No line break for the moment, may be turned into
83 UC_BREAK_POSSIBLE later, via last_p. */
86 *p = UC_BREAK_PROHIBITED;
88 w = uc_width (uc, encoding);
89 if (w >= 0) /* ignore control characters in the string */
99 /* The last atomic piece of text ends here. */
100 if (last_p != NULL && last_column + piece_width + at_end_columns > width)
102 /* Insert a line break. */
103 *last_p = UC_BREAK_POSSIBLE;
107 return last_column + piece_width;
117 /* Read the contents of an input stream, and return it, terminated with a NUL
120 read_file (FILE *stream)
128 while (! feof (stream))
130 if (size + BUFSIZE > alloc)
132 alloc = alloc + alloc / 2;
133 if (alloc < size + BUFSIZE)
134 alloc = size + BUFSIZE;
135 buf = realloc (buf, alloc);
138 fprintf (stderr, "out of memory\n");
142 count = fread (buf + size, 1, BUFSIZE, stream);
154 buf = realloc (buf, size + 1);
157 fprintf (stderr, "out of memory\n");
166 main (int argc, char * argv[])
170 /* Insert line breaks for a given width. */
171 int width = atoi (argv[1]);
172 char *input = read_file (stdin);
173 int length = strlen (input);
174 char *breaks = malloc (length);
177 u8_width_linebreaks ((uint8_t *) input, length, width, 0, 0, NULL, "UTF-8", breaks);
179 for (i = 0; i < length; i++)
183 case UC_BREAK_POSSIBLE:
186 case UC_BREAK_MANDATORY:
188 case UC_BREAK_PROHIBITED:
193 putc (input[i], stdout);